Research map / Video / Video segmentation and tracking
MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Combine semantic, distortion, and motion features (ablation) | MD-VQA · LIVE-WC, YT-UGC+, and TaoLive | SRCC: LIVE-WC: 0.925 -> 0.931; YT-UGC+: 0.805 -> 0.822; TaoLive: 0.940 -> 0.942 | Helped |
| Add distortion features to semantic features (ablation) | MD-VQA · LIVE-WC, YT-UGC+, and TaoLive | SRCC: LIVE-WC: 0.911 -> 0.925; YT-UGC+: 0.785 -> 0.805; TaoLive: 0.931 -> 0.935 | Helped |
| Add motion features to semantic features (ablation) | MD-VQA · LIVE-WC, YT-UGC+, and TaoLive | SRCC: LIVE-WC: 0.911 -> 0.921; YT-UGC+: 0.785 -> 0.792; TaoLive: 0.931 -> 0.940 | Helped |
| Add semantic features to distortion and motion features (ablation) | MD-VQA · LIVE-WC, YT-UGC+, and TaoLive | SRCC: LIVE-WC: 0.857 -> 0.931; YT-UGC+: 0.573 -> 0.822; TaoLive: 0.925 -> 0.942 | Helped |
| Add adjacent-frame absolute feature error (ablation) | MD-VQA · LIVE-WC, YT-UGC+, and TaoLive | SRCC: LIVE-WC: 0.912 -> 0.931; YT-UGC+: 0.814 -> 0.822; TaoLive: 0.925 -> 0.942 | Helped |
| Use the feature fusion module instead of simple concatenation (ablation) | MD-VQA · LIVE-WC, YT-UGC+, and TaoLive | SRCC: LIVE-WC: 0.913 -> 0.931; YT-UGC+: 0.811 -> 0.822; TaoLive: 0.921 -> 0.942 | Helped |
| Use MD-VQA rather than SimpleVQA | VQA models · KoNViD-1k | SRCC: 0.856 -> 0.851 | Hurt |
| Use MD-VQA rather than SimpleVQA | VQA models · LIVE-VQC | PLCC: 0.815 -> 0.839 | Helped |
Closest papers by meaning
- FineVQ: Fine-Grained User Generated Content Video Quality Assessment (CVPR 2025 · similarity 0.89)
- KVQ: Kwai Video Quality Assessment for Short-form Videos (CVPR 2024 · similarity 0.86)
- PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild (CVPR 2024 · similarity 0.85)
- AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM (CVPR 2025 · similarity 0.84)
- Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs (CVPR 2025 · similarity 0.84)
- KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception (CVPR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.